Arrow Research search

Author name cluster

Kaiyi Xu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
1 author row

Possible papers

2

AAAI Conference 2026 Conference Paper

SynWeather: Weather Observation Data Synthesis Across Multiple Regions and Variables via a General Diffusion Transformer

  • Kaiyi Xu
  • Junchao Gong
  • Zhiwang Zhou
  • Zhangrui Li
  • Yuandong Pu
  • Yihao Liu
  • Ben Fei
  • Fenghua Ling

With the advancement of meteorological instruments, abundant data has become available. However, due to instruments’ intrinsic limitations such as environmental sensitivity and orbital constraints, raw data often suffer from temporal or spatial gaps, making it urgent to leverage data synthesis techniques to fill in missing information. Current approaches are typically focus on single-variable, single-region tasks and primarily rely on deterministic modeling. This limits unified synthesis across variables and regions, overlooks cross-variable complementarity and often leads to over-smoothed results. To address above challenges, we introduce SynWeather, the first dataset designed for Unified Multi-region and Multi-variable Weather Observation Data Synthesis. SynWeather covers four representative regions: the Continental United States, Europe, East Asia, and Tropical Cyclone regions, as well as provides high-resolution observations of key weather variables, including Composite Radar Reflectivity, Hourly Precipitation, Visible Light, and Microwave Brightness Temperature. In addition, we introduce SynWeatherDiff, a general and probabilistic weather synthesis model built upon the Diffusion Transformer framework to address the over-smoothed problem. Experiments on the SynWeather dataset demonstrate the effectiveness of our network compared with both task-specific and general models. Moreover, SynWeatherDiff is able to generate results that are both fine-grained and accurate in high-value regions. Through the dataset and baseline model, we aim to advance meteorological downstream tasks and promote the development of general models for weather variable synthesis.

PDF Details DOI

EAAI Journal 2025 Journal Article

Cancer–drug response prediction via feature aggregation and association graph learning

  • Kaiyi Xu
  • Minhui Wang
  • Xin Zou
  • Chengfu Ji
  • Hua Zhou
  • Chang Tang

Predicting cancer–drug response (CDR) not only guides the development of anticancer drugs but also provides personalized treatment plans for cancer patients, driving the advancement of precision medicine. Currently, numerous computational methods are utilized for CDR prediction and achieve great achievements. However, there are still some issues need to be addressed. From the aspect of data using, many studies primarily use single nucleotide variations (SNV) as features of cell lines, yet their acquisition from clinical data is often incomplete and inefficient, making it challenging to extend SNV-based CDR models from in vitro cell lines to clinical data. From the aspect of modeling, most works focus excessively on learning the intrinsic characteristics of drugs and cell lines, while neglecting to fully capture their interaction information and network-level knowledge. In this paper, we introduce a feature aggregation and association graph learning network (F A 2 GL) for CDR, which aggregates intrinsic and interaction feature representations of drugs and cell lines, and obtains their network-level knowledge from the association graph. In this network, F A 2 GL initially employs the self-attention block (SAB) to capture drug intrinsic features, with a focus on the relationships between substructures within the same drug, and utilizes the multilayer perceptron (MLP) to obtain cell line intrinsic features. Subsequently, it constructs the cross-attention block (CAB) to extract interaction information between drugs and cell lines, followed by the utilization of a fusion coefficient for aggregating these features. Additionally, F A 2 GL also constructs an association graph by introducing pipe nodes and similarity networks, bridging the feature gap between drugs and cell lines and enhancing predictions of similar substances, respectively. Then, a graph neural network (GNN) is applied to this graph to capture their network-level information. By integrating fine-grained and network-level features, F A 2 GL demonstrates competitiveness compared to state-of-the-art methods on Genomics of Drug Sensitivity in Cancer (GDSC) dataset which contains various cancers such as acute lymphoblastic leukemia, diffuse large B-Cell lymphoma, and multiple myeloma, while avoiding the use of large-scale SNV data. The codes and data for F A 2 GL are available at https: //github. com/Dtdtxuky/FA-2GL/tree/main.

Details DOI
v2026.09.13